def __init__()

in src/hyperpod_nemo_adapter/collections/model/nlp/custom_models/modeling_deepseek.py [0:0]

• 33 lines of code
• 8 McCabe index (conditional complexity)

    def __init__(self, config):
        super().__init__()
        self.config = config
        self.num_experts_per_tok = config.num_experts_per_tok

        if hasattr(config, "ep_size") and config.ep_size > 1:
            assert config.ep_size == dist.get_world_size()
            self.ep_size = config.ep_size
            self.experts_per_rank = config.n_routed_experts // config.ep_size
            self.ep_rank = dist.get_rank()
            self.experts = nn.ModuleList(
                [
                    (
                        DeepseekV3MLP(config, intermediate_size=config.moe_intermediate_size)
                        if i >= self.ep_rank * self.experts_per_rank and i < (self.ep_rank + 1) * self.experts_per_rank
                        else None
                    )
                    for i in range(config.n_routed_experts)
                ]
            )
        else:
            self.ep_size = 1
            self.experts_per_rank = config.n_routed_experts
            self.ep_rank = 0
            self.experts = nn.ModuleList(
                [
                    DeepseekV3MLP(config, intermediate_size=config.moe_intermediate_size)
                    for i in range(config.n_routed_experts)
                ]
            )
        self.gate = MoEGate(config)
        if config.n_shared_experts is not None:
            intermediate_size = config.moe_intermediate_size * config.n_shared_experts
            self.shared_experts = DeepseekV3MLP(config=config, intermediate_size=intermediate_size)